mcpscore: Instructions file for Codex

AGENTS.md

mcpscore AGENTS.md is an instructions file for Codex, OpenCode from mcp-box/mcpscore. It costs 1,409 tokens per session, scanned A, original, MIT.

Repository instructions for mcpscore, a tool that checks MCP servers against the MCP specification. They define required validation commands and rules for creating, versioning, scoping, and retiring checks.

In plain words
What is it for?
Use them when adding or changing mcpscore rules, documentation, tests, or validation behavior.
Why use it?
They prevent changes from breaking the project’s tests or changing stable rule identifiers and explain how specification changes should be handled.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mcp-box/mcpscore's own configuration. It tells Codex and OpenCode how to work on mcpscore itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpscore configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mcp-box/mcpscore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mcp-box/mcpscore/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mcp-box/mcpscore

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcpscore AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mcp-box/mcpscore/agents-md/github.svg)](https://agentmods.dev/instructions/mcp-box/mcpscore/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mcp-box/mcpscore/agents-md"><img src="https://agentmods.dev/badge/instructions/mcp-box/mcpscore/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcpscore AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mcp-box/mcpscore/agents-md"><img src="https://agentmods.dev/badge/instructions/mcp-box/mcpscore/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,409 This file is loaded in full into every session.
When invoked 1,409 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01409 $0.01409
Opus 5.5 $0.00564 $0.00564
Sonnet 5.5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 1mo ago against content hash 4529e2abc1ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpscore AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions for mcpscore

  • Run make all before handing off — it mirrors CI (lint, typecheck, tests + coverage). The gate is uv run pyright mcpscore/ and uv run ruff check — inline IDE diagnostics may differ; the commands are authoritative.
  • rule_id is a stable public contract: never rename or reuse one. New rules must cite the MCP spec section (or SEP) they enforce in their result details.
  • Rule lifecycle — three states, and the choice between them matters:
    1. Active — runs everywhere.
    2. Version-scoped — set min_spec_version/max_spec_version when a rule is correct but only for some revisions. Use this for anything the spec removed or deprecated: the rule keeps its ID and still judges servers on the revisions where the requirement held. Obsolescence is scoping, not deletion.
    3. Retired — delete the rule only when it was wrong (it asserted something the spec does not require, or contradicted another rule), and add an entry to mcpscore/rules/retired.py. That registry generates the "Retired rules" table in docs/rules.mdx, so an old report or a stale CI waiver stays explainable. A retired ID is never reused — a test enforces it.
  • Readiness rules (group_name = "readiness") score on the readiness axis; since the 1.1.0 promotion they ALSO count in the main score, but only for modern-lifecycle servers (era modern/dual-era) in full audits — never for legacy servers, never in partial audits (readiness_promoted in mcp_auditor.py is the single switch). Rules that cannot judge anything return a skip reason — they never fail a server for missing observations.
  • Probes must never invoke tools/call against a target server — audits must be free of tool side effects. Probes never raise; network failures are ProbeOutcome.ERROR data. The ONE surface allowed to call tools is the opt-in --smoke mode (smoke.py, CLI-only): its results never enter the score, it never runs from probes/rules or the web service, and its safety default (readOnlyHint-only unless --call-all) must not be weakened.
  • docs/rules.mdx is generated — edit scripts/generate_rules_doc.py and run make docs-rules, never the file itself. CI fails on drift.
  • Docs are MDX served by Mintlify from docs/ — pages need frontmatter; validate with make docs-check.
  • For each new feature: update the docs and add a CHANGELOG entry (Keep a Changelog format). Docstrings: imperative first line, ≤120-char lines.
  • Do not commit to main; work on a branch. Do not add strategy or planning documents to this repository — it is public.
  • docs-live is a deploy pointer, never a working branch — and never delete it (nor main; both are deletion-protected by repository rulesets since 2026-08-27). Mintlify serves docs.mcpscore.dev from docs-live; publish-docs.yml force-pushes it to each stable release tag. Deleting it takes the docs site down; committing to it gets overwritten at the next release. Docs changes go through main like everything else and reach the site at the next release.

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +7 lines · +71 tokens per session 4529e2abc1ed
  2. 2mo ago Changed · +3 lines · +70 tokens per session fd4b2d3b952d
  3. 2mo ago First seen · 71 lines · 1,268 tokens per session scan A 0615f9d85010

Subscribe to this mod's changes

mcpscore AGENTS.md is an instructions file published in the GitHub repository mcp-box/mcpscore (42 stars, last pushed 2d ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0056 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

mcpscore AGENTS.md compared with instructions from other repositories

mcpscore AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcpscore AGENTS.mdmcp-box/mcpscoreInstructions file422d agoMITA1,409Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode